Computation of Optimal Transport and Related Hedging Problems via Penalization and Neural Networks
Published in
Applied Mathematics and Optimization(2018)External Links:
TL
TL;DR
This paper presents a widely applicable approach to solving (multi-marginal, martingale) optimal transport and related problems via neural networks through penalizing the optimization problem in its dual formulation and reducing it to a finite dimensional one which corresponds to optimizing a neural network with smooth objective function.
Abstract
This paper presents a widely applicable approach to solving (multi-marginal, martingale) optimal transport and related problems via neural networks. The core idea is to penalize the optimization problem in its dual formulation and reduce it to a finite dimensional one which corresponds to optimizing a neural network with smooth objective function. We present numerical examples from optimal transport, martingale optimal transport, portfolio optimization under uncertainty and generative adversarial networks that showcase the generality and effectiveness of the approach.
References59 items
1
Smoothing Operators in Multi-Marginal Optimal Transport
2
A Review on Ambiguity in Stochastic Portfolio Optimization
3
Robust risk aggregation with neural networks
4
Deep hedging
5